13 citations · 17 across the 2 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023★ 4 cited
Improving Pixel-based MIM by Reducing Wasted Modeling Capability
Yuan Liu, Songyang Zhang, Jiacheng Chen +3
There has been significant progress in Masked Image Modeling (MIM). Existing MIM methods can be broadly categorized into two groups based on the reconstruction target: pixel-based…
cs.CV2023★ 13 cited
PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling
Yuan Liu, Songyang Zhang, Jiacheng Chen +2
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new…